Skip to content
Metered.
Mistral AI model

Mistral Small 3.2 24B

API pricing per million tokens

mistral-small-3-2-24b-instruct Open weightsChecked 8h ago
Cost calculator Compare
Input
$0.075
per 1M, DeepInfra (fp8)
Output
$0.2
per 1M tokens
Cached input
n/a
no batch tier listed
Context
256K
16K max output

Where to buy it (3)

  • DeepInfrafp8, fp8$0.075 / $0.2$0.106 blended
  • Venicefp8, fp8$0.094 / $0.25$0.133 blended
  • Parasailbf16, bf16$0.09 / $0.3cached $0.05

Through a gateway

Your own numbers

100M input and 20M output tokens a month: $11.50 direct.

Related models

About Mistral Small 3.2 24B

Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling.

Takes image, text in and returns text. First listed Sep 23, 2026. Blended price $0.106 per 1M tokens at 3 input to 1 output.

OpenRouter listing Mistral AI pricing page
Across fru.devCompany profileSeries D, $3.6B (2026-09)12 releases, latest 2026-09-16

Questions

How much does Mistral Small 3.2 24B cost?

$0.075 per million input tokens and $0.2 per million output tokens.

What is the context window of Mistral Small 3.2 24B?

256K tokens, with up to 16K tokens of output.

Where is Mistral Small 3.2 24B cheapest?

Of 3 routes tracked, DeepInfra is cheapest at $0.075 input and $0.2 output per million tokens.

List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.

Weekly: LLM API list prices that changed, Thursday mornings.